Aldo A Faisal — accepted AI-conference papers

2025

Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning

Gianluca Drappo, Arnaud Robert, Marcello Restelli, Aldo A. Faisal, Alberto Maria Metelli, Ciara Pike-Burke

AISTATS 2025poster

We study goal-conditioned Hierarchical Reinforcement Learning (HRL), where a high-level agent instructs sub-goals to a low-level agent. Under the assumption of a sparse reward function and known hierarchical decomposition, we propose a new algorithm to learn optimal hierarchical policies. Our algori…

Cited by 0 Source ↗Scholar ↗

2025

Variational Uncertainty Decomposition for In-Context Learning

I. Shavindra Jayasekera, Jacob Si, Filippo Valdettaro, Wenlong Chen, Aldo A. Faisal, Yingzhen Li

NeurIPS 2025poster

As large language models (LLMs) gain popularity in conducting prediction tasks in-context, understanding the sources of uncertainty in in-context learning becomes essential to ensuring reliability. The recent hypothesis of in-context learning performing predictive Bayesian inference opens the avenue…

Cited by 0 Source ↗Scholar ↗

2023

Sample Complexity of Goal-Conditioned Hierarchical Reinforcement Learning

Arnaud Robert, Ciara Pike-Burke, Aldo A. Faisal

NeurIPS 2023poster

Hierarchical Reinforcement Learning (HRL) algorithms can perform planning at multiple levels of abstraction. Empirical results have shown that state or temporal abstractions might significantly improve the sample efficiency of algorithms. Yet, we still do not have a complete understanding of the bas…

Cited by 6 Source ↗PDF ↗Scholar ↗

2018

Representation Balancing MDPs for Off-policy Policy Evaluation

Yao Liu, Omer Gottesman, Aniruddh Raghu, Matthieu Komorowski, Aldo A Faisal, Finale Doshi-Velez +1

NeurIPS 2018poster

We study the problem of off-policy policy evaluation (OPPE) in RL. In contrast to prior work, we consider how to estimate both the individual policy value and average policy value accurately. We draw inspiration from recent work in causal reasoning, and propose a new finite sample generalization err…

Cited by 87 Source ↗PDF ↗Scholar ↗